SEAS Search – GenAI Academic Advisor

SEAS Search is a production-grade AI-powered academic advising system built for The George Washington University's School of Engineering and Applied Science. The system combines Knowledge Graph construction with Retrieval-Augmented Generation (RAG) to answer complex, multi-hop questions about course prerequisites, degree requirements, and academic policies.

The architecture features a vector database for semantic search over university course data, integrated with a fine-tuned Llama 3.1 model using LoRA adapters. The fine-tuning approach used 14x less training data compared to full fine-tuning while achieving 25x faster training times, making the system practical for academic deployment.

The full-stack application is deployed on Vercel with real-time semantic search capabilities, comprehensive error handling, rate limiting, and a complete CI/CD pipeline. The frontend provides an intuitive chat interface where students can ask natural language questions about their academic journey.